cjR d Z dZdZddlZddlZddlmZmZ ddl ddl m
Z
e e
D cg c]
} | d d k7 s | c} g d
z Z [
e
d Zd Zd
Zd ZdZdZe edez z ee z ZdZdZdZdZ edd Z eeeee Z dZ edd ee z Z de z Z ee e Z ed e d z Z! ee!e e Z"d Z#d Z$d Z%d!Z&d"Z' ee'd#z e'd$z Z( ee'd%z e'd&z Z) ed'd(d)d*d+d,d-d.d/ Z*d0Z+ ed1d2d3 Z, ee*e+e, Z- ee"e-e)e Z.ee.z Z/ ee'd4z ed5d z e'd6z ed7d z Z0 edee( Z1e ee1e"e-e0e z Z2 e3ejh e/e2e%e&f \ Z5Z6Z7Z8 ed8d9d:d; ed8d9dz Z9 ejh e# ejh e$ e7e8d?e9D ci c] }| d#e7
c}e9D ci c] }| d$e8
c}e9D ci c] }|d c}Z:d#d$he9D ch c] }| d# c}z e9D ch c] }| d$ c}z Z;d5d7he9D ch c] }| d5 c}z e9D ch c] }| d7 c}z Z Z? G dC dDe> Z@dE ZAeAfdFZBdG ZC G dH dI ZD ejh dJej ZF ejh dKej ZGdL ZHdM ZIdN ZJdO ZKeLdPk( r\ddlMZM eNeMj dkD r& eB ePeMj d j y eBeMj j yyc c} w # e$ r eZ
Y w xY wc c}w c c}w c c}w c c}w c c}w c c}w c c}w )Qa Tokenization help for Python programs.
generate_tokens(readline) is a generator that breaks a stream of
text into Python tokens. It accepts a readline-like method which is called
repeatedly to get the next line of input (or "" for EOF). It generates
5-tuples with these members:
the token type (see token.py)
the token (a string)
the starting (row, column) indices of the token (a 2-tuple of ints)
the ending (row, column) indices of the token (a 2-tuple of ints)
the original line (string)
It is designed to match the working of the Python tokenizer exactly, except
that it produces COMMENT tokens for comments and gives type OP for all
operators
Older entry points
tokenize_loop(readline, tokeneater)
tokenize(readline, tokeneater=printtoken)
are the same, except instead of generating tokens, tokeneater is a callback
function to which the 5 fields described above are passed as 5 arguments,
each time a new token is found.zKa-Ping Yee z@GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, Skip Montanaro N)BOM_UTF8lookup)* )token_)tokenizegenerate_tokens
untokenizec 0 ddj | z dz S )N(|))joinchoicess //usr/lib64/python3.12/lib2to3/pgen2/tokenize.pygroupr 0 s C#((7"3 3c 99 c t | dz S )Nr r r s r anyr 1 s %/C//r c t | dz S )N?r r s r mayber 2 s E7Oc 11r c , t fd D S )Nc 3 K | ]5 }d z D ]+ }|j |j k7 s%||z - 7 yw)) N)casefold).0xyls r z _combinations..4 s8 !!e)Qqzz|qzz|/KA)qs .> >)set)r# s `r
_combinationsr& 3 s r z[ \f\t]*z #[^\r\n]*z\\\r?\nz\w+z0[bB]_?[01]+(?:_[01]+)*z(0[xX]_?[\da-fA-F]+(?:_[\da-fA-F]+)*[lL]?z 0[oO]?_?[0-7]+(?:_[0-7]+)*[lL]?z[1-9]\d*(?:_\d+)*[lL]?z0[lL]?z[eE][-+]?\d+(?:_\d+)*z \d+(?:_\d+)*\.(?:\d+(?:_\d+)*)?z\.\d+(?:_\d+)*z \d+(?:_\d+)*z\d+(?:_\d+)*[jJ]z[jJ]z[^'\\]*(?:\\.[^'\\]*)*'z[^"\\]*(?:\\.[^"\\]*)*"z%[^'\\]*(?:(?:\\.|'(?!''))[^'\\]*)*'''z%[^"\\]*(?:(?:\\.|"(?!""))[^"\\]*)*"""z'(?:[uUrRbBfF]|[rR][fFbB]|[fFbBuU][rR])?'''"""z '[^\n'\\]*(?:\\.[^\n'\\]*)*'z "[^\n"\\]*(?:\\.[^\n"\\]*)*"z\*\*=?z>>=?z<<=?z<>z!=z//=?z->z[+\-*/%&@|^=<>]=?~z[][(){}]z\r?\nz:=z[:;.,`@]z'[^\n'\\]*(?:\\.[^\n'\\]*)*'z"[^\n"\\]*(?:\\.[^\n"\\]*)*"rRfFbB> UuURUruRur)r* r+ r' r( c e Zd Zy)
TokenErrorN__name__
__module__ __qualname__ r r r: r: r r: c e Zd Zy)StopTokenizingNr; r? r r rB rB r@ r rB c ` |\ }}|\ }}t d||||t | t | fz y )Nz%d,%d-%d,%d: %s %s)printtok_namerepr) typer xxx_todo_changemexxx_todo_changeme1linesrowscolerowecols r
printtokenrO s< $LT4%LT4
tT4$ e= > ?r c < t | | y# t $ r Y yw xY w)a:
The tokenize() function accepts two parameters: one representing the
input stream, and one providing an output mechanism for tokenize().
The first parameter, readline, must be a callable object which provides
the same interface as the readline() method of built-in file objects.
Each call to the function should return one line of input as a string.
The second parameter, tokeneater, must also be a callable object. It is
called once for each token, with five arguments, corresponding to the
tuples generated by generate_tokens().
N)
tokenize_looprB )readline
tokeneaters r r r s#
h
+
s c . t | D ] } || y N)r
)rR rS
token_infos r rQ rQ s %h/
J 0r c $ e Zd Zd Zd Zd Zd Zy) Untokenizerc . g | _ d| _ d| _ y )Nr r )tokensprev_rowprev_col)selfs r __init__zUntokenizer.__init__ s
r c |\ }}|| j k sJ || j z
}|r | j j d|z y y )N )r[ r\ rZ append)r] startrowcol
col_offsets r add_whitespacezUntokenizer.add_whitespace sJ Sdmm###4==(
KK sZ / 0 r c f |D ] }t | dk( r| j || np|\ }}}}}| j | | j j | |\ | _ | _ |t t fv sw| xj
dz
c_ d| _ dj | j S )N r r r )
lencompatrf rZ ra r[ r\ NEWLINENLr )r] iterablettok_typer rb endrJ s r r zUntokenizer.untokenize s A1v{ Ax(01 -HeUC & KK u %+. (DM4=GR=(
"
!
wwt{{##r c d}g }| j j }|\ }}|t t fv r|dz
}|t t
fv rd}|D ] }|d d \ }}|t t t t fv r|dz
}|t k( r|j | C|t k( r|j ]|t t
fv rd}n|r|r
||d d} || y )NFr` Trh ) rZ ra NAMENUMBERrk rl ASYNCAWAITINDENTDEDENTpop) r] r rm startlineindents toks_appendtoknumtokvaltoks r rj zUntokenizer.compat s kk(( dF^ # cMF gr] " IC !WNFF$u55#
v&6!
GR=( wGBK( ! # r N)r< r= r> r^ rf r rj r? r r rX rX s
1 $ r rX z&^[ \t\f]*#.*?coding[:=][ \t]*([-\w.]+)s ^[ \t\f]*(?:[#\r\n]|$)c | dd j j dd }|dk( s|j d ry|dv s|j d ry | S )
z(Imitates get_normal_name in tokenizer.c.N r -utf-8zutf-8-)zlatin-1
iso-8859-1z iso-latin-1)zlatin-1-z iso-8859-1-z iso-latin-1-r )lowerreplace
startswith)orig_encencs r _get_normal_namer sX 3B-
'
'S
1C
g~ 1
66
~~AB Or c dd}d} fd}fd} | }|j t r d|dd }d}|s|g fS || }|r||gfS t j | s||gfS | }|s||gfS || }|r|||gfS |||gfS ) a
The detect_encoding() function is used to detect the encoding that should
be used to decode a Python source file. It requires one argument, readline,
in the same way as the tokenize() generator.
It will call readline a maximum of twice, and return the encoding used
(as a string) and a list of any lines (left as bytes) it has read
in.
It detects the encoding from the presence of a utf-8 bom or an encoding
cookie as specified in pep-0263. If both a bom and a cookie are present, but
disagree, a SyntaxError will be raised. If the encoding cookie is an invalid
charset, raise a SyntaxError. Note that if a utf-8 bom is found,
'utf-8-sig' is returned.
If no encoding is specified, then the default of 'utf-8' will be returned.
FNr c F S # t $ r
t cY S w xY wrU )
StopIterationbytes)rR s r read_or_stopz%detect_encoding..read_or_stop s& : 7N s
c > | j d }t j | }|sy t |j d } t
| }r |j dk7 r t d |dz
}|S # t $ r Y y w xY w# t $ r t d|z w xY w)Nasciir zunknown encoding: r zencoding problem: utf-8z-sig)
decodeUnicodeDecodeError cookie_rematchr r r LookupError SyntaxErrorname)rJ line_stringr encodingcodec bom_founds r find_cookiez$detect_encoding..find_cookie s ++g.K ,#EKKN3 ?8$E
zzW$!";<< H# " ? 2X => > ?s A5 B 5 B BB T z utf-8-sig)r r blank_rer )rR r defaultr r firstsecondr s ` @r detect_encodingr s $ IHG ,
NE ! ab {5!H% >>%
^F 6"H% (( UFO ##r c 8 t }|j | S )a Transform tokens back into Python source code.
Each element returned by the iterable must be a token sequence
with at least two elements, a token number and token value. If
only two tokens are passed, the resulting output is poor.
Round-trip invariant for full input:
Untokenized source will match input source exactly
Round-trip invariant for limited input:
# Output text will tokenize the back to the input
t1 = [tok[:2] for tok in generate_tokens(f.readline)]
newcode = untokenize(t1)
readline = iter(newcode.splitlines(1)).next
t2 = [tok[:2] for tokin generate_tokens(readline)]
assert t1 == t2
)rX r )rm uts r r r : s $
B
== ""r c #
K dx}x}}d\ }}d}dg}d}d} d}
d} | } |dz }dt | }}
|r| s t d j | }|r4|j d x}
}t
|| d| z ||f|| z f d\ }}d}n|r0| dd d k7 r(| d
d d k7 r t || z |t | f|f d}d}|| z }|| z }|dk( r|s| sn/d}|
|k rA| |
d k( r|dz }n(| |
d
k( r|t z dz t z }n | |
dk( rd}nn |
dz }
|
|k rA|
|k( rn|r| d}| |
dv r| |
dk( r]| |
d j d }|
t | z }t |||
f||
t | z f| f t | |d ||f|t | f| f n,t t f| |
dk( | |
d ||
f|t | f| f ||d kD r%|j | t | d|
|df||
f| f ||d k rC||vrt dd||
| f |dd }| r|
|d k\ rd} d} d}
t d||
f||
f| f ||d k rC| r#| r!|
|d k\ rd} d} d}
n| st d|df d}|
|k rt j | |
}|r]|j! d \ }}||f||f|}
}}| || | | }}|t" j$ v s
|dk( r|dk7 rt& |||| f n&|dv r)t( } |dkD rt } n| rd} |r| d}| |||| f n|dk( r+ |j* d rJ |r| d}t |||| f n|t, v rYt. | }|j | |
}|r/|j d }
| ||
}|r| d}t
||||
f| f nu||f}| |d }| }no|t0 v s|dd t0 v s |dd t0 v rR|d dk( r4||f}t. | xs t. |d xs t. |d }| |d d}}| }n|r| d}t
|||| f n|j3 r|dv r | r|d k( rt4 nt6 |||| f t8 |||| f} |d k( r|s| }|d v r=|r;|d t8 k( r/|d d k( r'|d k( rd} |d }
t4 |d |d |d |d f d}|r| d}| nd|d k( r|r| d}t ||||
f| f d}nE|d!v r|dz }n |d"v r|dz
}|r| d}t: |||| f n t | |
||
f||
dz f| f |
dz }
|
|k r|r| d}|dd D ] } t d|df|dfdf t< d|df|dfdf y# t $ r d} Y %w xY ww)#a4
The generate_tokens() generator requires one argument, readline, which
must be a callable object which provides the same interface as the
readline() method of built-in file objects. Each call to the function
should return one line of input as a string. Alternately, readline
can be a callable function terminating with StopIteration:
readline = open(myfile).next # Example of alternate readline
The generator produces 5-tuples with these members: the token type; the
token string; a 2-tuple (srow, scol) of ints specifying the row and
column where the token begins in the source; a 2-tuple (erow, ecol) of
ints specifying the row and column where the token ends in the source;
and the line on which the token was found. The line passed is the
physical line.
r )r r NFr r zEOF in multi-line stringz\
z\
r` z#
#z
rr z3unindent does not match any outer indentation levelz
zEOF in multi-line statement.T
rh r )asyncawaitr )defforr \z([{z)]}) r ri r: r rp STRING
ERRORTOKENtabsizerstripCOMMENTrl ra rw IndentationErrorrx
pseudoprogspanstringdigitsrt rk endswith
triple_quotedendprogs
single_quoted isidentifierru rv rs OP ENDMARKER) rR lnumparenlev continuedcontstrneedcontcontliner{ stashed async_defasync_def_indent async_def_nlrJ posmaxstrstartendprogendmatchrp column
comment_tokennl_pos pseudomatchrb sposeposr initialnewliner indents r r
r
O s #$#D#8i GXHcG GIL
:D axc$iS !;XFF }}T*H $LLO+c wds 3 $ho? ?$)! d23i6 1d23i86K!7T>#dCI%6B B !D.#d?
]9F)9#fqjV#Y$&&'/A2Ew1N#Y$&Ag ) cz5
CyG#9#$(J$5$5f$=M 3}#5 5F"M #;sS 5G/G(H$P P tFG} &>D#d)+'"+.M ! $ #$ !>q JJICi$**45K ( - -a 0
s#'-$cCd!%eC $u+wfmm+sNu|!5$d;; & %G !|"$"'+ %
"&"E4t<< ^ -u~~d 333 %
"&"E4t<<m+ &uoG &}}T3 7H &ll1o $U3"")M&*G %udT3K FF$(%="&uv,#'
-"1I ."1I . RyD($(%=#+G#4 $6q8J $6#+E!H#5 ,0L!#' "")M&*G %udD$ ?? ))+ 22$,1W,<5%#($d#< < $ dD9C '"% . #$+AJ$$6$+AJ'$9 $~,0 3:2; 0#('!*#*1:wqz#*1:#/ / '+G %
"& I _ %
"& udT3K>> !I %'HqL E)hl8 %
"& udD$77!49 #;s1u
t= =AgS Cii ~
!"+rD!9tQi44 b4)dAY
33E D s< U
T; C:U
D U
KU
7U
; U
U
U
U
__main__)S__doc__
__author__ __credits__r recodecsr r lib2to3.pgen2.tokenr r dir__all__r NameErrorstrr r r r&
WhitespaceCommentIgnoreName Binnumber Hexnumber Octnumber Decnumber IntnumberExponent
PointfloatExpfloat Floatnumber
ImagnumberNumberSingleDoubleSingle3Double3
_litprefixTripleStringOperatorBracketSpecialFunny
PlainTokenTokenContStr PseudoExtras PseudoTokenmapcompile tokenprogr single3prog double3prog _strprefixesr r r r Exceptionr: rB rO r rQ rX ASCIIr r r r r r
r< sysri argvopenrR stdin)r! prefixs 00r r s #0 *
F # ! %j
0jAaDCK1j
0 4, , : / 1
c*z12 2U7^ C
& 7 . +X 6 )Y 9 = #
57H
IERZO
[
X %J)
& g(=
>
z; 2
$ #
2
2
7
zE!:#5 6 z ;; ;;
= GWeU%%
%
-
h)
65&$
/
;;c:&' ;;c:&' ( Z&1 5 vugtLL 25JJ Wg638 / :{K #sC%#sC%&&'
F#*"**V*< { 99EF v&~{* F 9 :FF v&~{* F 9 +77,vt|,7 9 EN"./,xs^,/0"./,xs^,/0 #J ,- fxq\ -. ,- fxq\ -. ! ! %Y %? #-
& 6 6 p
BJJ@"(( K 2::0"(( ; G$R#*`4D z
388}q(4 #4#=#=>
399%%
& Y 1
E\ GF7 0/ .-sF
L$L$L)
L7
L<)
M> M M * M> M)L43L4